This repository contains the model used in the paper
Aether: Geometric-Aware Unified World Modeling.
Aether addresses a fundamental challenge in AI: integrating geometric reconstruction with generative modeling
for human-like spatial reasoning. Our framework unifies three core capabilities: (1) 4D dynamic reconstruction,
(2) action-conditioned video prediction, and (3) goal-conditioned visual planning. Trained entirely on
synthetic data, Aether achieves strong zero-shot generalization to real-world scenarios.
1@article{aether,
2 title = {Aether: Geometric-Aware Unified World Modeling},
3 author = {Aether Team and Haoyi Zhu and Yifan Wang and Jianjun Zhou and Wenzheng Chang and Yang Zhou and Zizun Li and Junyi Chen and Chunhua Shen and Jiangmiao Pang and Tong He},
4 journal = {arXiv preprint arXiv:2503.18945},
5 year = {2025}
6}
This repository is licensed under the MIT License - see the
LICENSE file for details.
Our work is primarily built upon
Accelerate,
Diffusers,
CogVideoX,
Finetrainers,
DepthAnyVideo,
CUT3R,
MonST3R,
VBench,
GST,
SPA,
DroidCalib,
Grounded-SAM-2,
ceres-solver, etc.
We extend our gratitude to all these authors for their generously open-sourced code and their significant contributions to the community.
